Quality control - Distributions - DIPG Batch 1
Sophie Herbst
Analysis date: 2023-09-18
Depends on
CRC_Xenografts_FirstBatch_DataProcessing Script
load("../Data/Cache/Xenografts_Batch1_2_DataProcessing.RData")TODO
Setup
Load libraries and functions
Quality control
Nr. phospho sites
print( paste( nrow(pY_Set1) , "pY peptides passed the filtering procedure for Set 1. These peptides were detected from", length(unique(pY_Set1$HGNC_Symbol) ), "proteins." ))## [1] "254 pY peptides passed the filtering procedure for Set 1. These peptides were detected from 174 proteins."#print( paste( nrow(pST_Set1) , "pST peptides passed the filtering procedure for Set 1. These peptides were detected from", length(unique(pST$HGNC_Symbol) ), "proteins." ))
print( paste( nrow(pY_Set2) , "pY peptides passed the filtering procedure for Set 2. These peptides were detected from", length(unique(pY_Set2$HGNC_Symbol) ), "proteins." ))## [1] "627 pY peptides passed the filtering procedure for Set 2. These peptides were detected from 389 proteins."#print( paste( nrow(pST_Set2) , "pST peptides passed the filtering procedure for Set 2. These peptides were detected from", length(unique(pST$HGNC_Symbol) ), "proteins." ))
print( paste( nrow(pY_noNA) , "pY peptides passed the filtering procedure for the sets combined. These peptides were detected from", length(unique(pY_noNA$HGNC_Symbol) ), "proteins." ))## [1] "231 pY peptides passed the filtering procedure for the sets combined. These peptides were detected from 163 proteins."#print( paste( nrow(pST_noNA) , "pST peptides passed the filtering procedure for the sets combined. These peptides were detected from", length(unique(pST_noNA$HGNC_Symbol) ), "proteins." ))Nr. proteins whole proteome
print( paste( length(unique(prot_Set1$HGNC_Symbol) ), "proteins detected in Set 1." ))
print( paste( length(unique(prot_Set2$HGNC_Symbol) ), "proteins detected in Set 2." ))
print( paste( length(unique(prot_top3peptidemedian$HGNC_Symbol) ), "proteins detected in both Sets." ))Distributions
pY Abundances
Set 1
pY_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Raw abundances")## Warning: Removed 374 rows containing non-finite values (`stat_density()`).
pY_Set1 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Abundances normalised to sup")## Warning: Removed 358 rows containing non-finite values (`stat_density()`).
pY_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Raw abundances")
pY_Set1 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Abundances normalised to sup")
pY_Set1 %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to bridge")
Set 2
pY_Set2 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Raw abundances")## Warning: Removed 591 rows containing non-finite values (`stat_density()`).
pY_Set2 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Abundances normalised to sup")## Warning: Removed 597 rows containing non-finite values (`stat_density()`).
pY_Set2 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Raw abundances")
pY_Set2 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Abundances normalised to sup")
pY_Set2 %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to bridge")
Combined
Colored by treatment
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_"), drop = F) %>%
separate( Sample , into = c("xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
ggplot(aes(value, fill= treatment, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
ggplot(aes(Sample, value, fill= treatment)) +
geom_boxplot() +
ggtitle("log2FC to normal") +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
group_by(Sample, treatment, day, replicate, set) %>%
summarise(mean_value = mean(value)) %>%
ggplot(aes(treatment, mean_value, fill= treatment)) +
geom_boxplot() +
ggbeeswarm::geom_beeswarm() +
ggtitle("log2FC to normal") +
ggpubr::stat_compare_means() +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])## `summarise()` has grouped output by 'Sample', 'treatment', 'day', 'replicate'.
## You can override using the `.groups` argument.
Colored by day
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_"), drop = F) %>%
separate( Sample , into = c("xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
ggplot(aes(value, fill= day, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
group_by(Sample, treatment, day, replicate, set) %>%
summarise(mean_value = mean(value)) %>%
ggplot(aes(day, mean_value, fill= day)) +
geom_boxplot() +
ggbeeswarm::geom_beeswarm() +
ggtitle("log2FC to normal") +
ggpubr::stat_compare_means() +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])## `summarise()` has grouped output by 'Sample', 'treatment', 'day', 'replicate'.
## You can override using the `.groups` argument.
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
group_by(Sample, treatment, day, replicate, set) %>%
summarise(mean_value = mean(value)) %>%
ggplot(aes(day, mean_value, fill= day)) +
geom_boxplot() +
ggbeeswarm::geom_beeswarm() +
ggtitle("log2FC to normal") +
ggpubr::stat_compare_means() +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)]) +
facet_grid(~treatment)## `summarise()` has grouped output by 'Sample', 'treatment', 'day', 'replicate'.
## You can override using the `.groups` argument.## Warning: Computation failed in `stat_compare_means()`
## Caused by error:
## ! argument "x" is missing, with no default
Colored by Prep
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_"), drop = F) %>%
separate( Sample , into = c("xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
mutate(prep = unlist(prep_l[Sample] )) %>%
ggplot(aes(value, fill= prep, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
mutate(prep = unlist(prep_l[Sample] )) %>%
group_by(Sample, treatment, day, replicate, set, prep) %>%
summarise(mean_value = mean(value)) %>%
ggplot(aes(prep, mean_value, fill= prep)) +
geom_boxplot() +
ggbeeswarm::geom_beeswarm() +
ggtitle("log2FC to normal") +
ggpubr::stat_compare_means() +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])## `summarise()` has grouped output by 'Sample', 'treatment', 'day', 'replicate',
## 'set'. You can override using the `.groups` argument.
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
mutate(prep = unlist(prep_l[Sample] )) %>%
group_by(Sample, treatment, day, replicate, set, prep) %>%
summarise(mean_value = mean(value)) %>%
#filter(treatment == "ctrl") %>%
ggplot(aes(prep, mean_value, fill= prep)) +
geom_boxplot() +
ggbeeswarm::geom_beeswarm() +
ggtitle("log2FC to normal") +
ggpubr::stat_compare_means() +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)]) +
facet_grid(day~treatment)## `summarise()` has grouped output by 'Sample', 'treatment', 'day', 'replicate',
## 'set'. You can override using the `.groups` argument.## Warning: Computation failed in `stat_compare_means()`
## Computation failed in `stat_compare_means()`
## Computation failed in `stat_compare_means()`
## Computation failed in `stat_compare_means()`
## Computation failed in `stat_compare_means()`
## Computation failed in `stat_compare_means()`
## Caused by error:
## ! argument "x" is missing, with no default
Colored by Set
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_"), drop = F) %>%
separate( Sample , into = c("xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
ggplot(aes(value, fill= set, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])
pY_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate( Sample , into = c( "xenograft", "treatment", "day", "replicate", "set"), sep = "_", remove = F) %>%
group_by(Sample, treatment, day, replicate, set) %>%
summarise(mean_value = mean(value)) %>%
ggplot(aes(set, mean_value, fill= set)) +
geom_boxplot() +
ggbeeswarm::geom_beeswarm() +
ggtitle("log2FC to normal") +
ggpubr::stat_compare_means() +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])## `summarise()` has grouped output by 'Sample', 'treatment', 'day', 'replicate'.
## You can override using the `.groups` argument.
pST Abundances
Set 1
pST_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Raw abundances")
pST_Set1 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Abundances normalised to sup")
pST_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Raw abundances")
pST_Set1 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Abundances normalised to sup")
pST_Set1 %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to bridge")Set 2
pST_Set2 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Raw abundances")
pST_Set2 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Abundances normalised to sup")
pST_Set2 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Raw abundances")
pST_Set2 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Abundances normalised to sup")
pST_Set2 %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to bridge")Combined
pST_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate(Sample, into = c("treatment", "replicate"), remove = F) %>%
ggplot(aes(value, fill= treatment, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)]) +
geom_vline(xintercept = 0)
pST_noNA %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate(Sample, into = c("treatment", "replicate"), remove = F) %>%
ggplot(aes(Sample, value, fill= treatment)) +
geom_boxplot() +
ggtitle("log2FC to bridge") +
theme_bw() +
theme(axis.text.x = element_text(angle = 90)) +
scale_fill_manual(values = PGPalette[c(1, 2, 4, 5)])
pST_noNA %>%
select(contains("log2FC")) %>%
select(!contains("normal")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate(Sample, into = c("treatment", "replicate"), remove = F) %>%
ggplot(aes(value, fill= treatment, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 5)])Whole proteome abundances
Set 1
prot_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
geom_density(alpha=0.5) +
xlim(0,10e5) +
ggtitle("Raw abundances")
prot_Set1 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10) +
ggtitle("Abundances normalised to sup")
prot_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Raw abundances")
prot_Set1 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Abundances normalised to sup")
prot_Set1 %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to bridge")Set 2
prot_Set2 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e5) +
ggtitle("Raw abundances")
prot_Set2 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10) +
ggtitle("Abundances normalised to sup")
prot_Set2 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Raw abundances")
prot_Set2 %>%
select(contains("TMTNorm_Abundance")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
scale_x_log10() +
ggtitle("Abundances normalised to sup")
prot_Set2 %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to bridge")Combined
prot_top3peptidemedian %>%
select(contains("log2FC")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal")
prot_top3peptidemedian %>%
select(contains("log2FC")) %>%
select(!contains("normal")) %>%
pivot_longer(names_to = "Sample", cols = everything()) %>%
mutate(Sample = str_remove(Sample, "log2FC_")) %>%
separate(Sample, into = c("treatment", "replicate"), remove = F) %>%
ggplot(aes(value, fill= treatment, group = Sample)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
ggtitle("log2FC to normal") +
theme_bw() +
scale_fill_manual(values = PGPalette[c(1, 2, 5)])
t(pST_mat_nonormal) %>%
as.data.frame( ) %>%
rownames_to_column( "peptide") %>%
pivot_longer(-peptide, names_to = "sample", values_to = "log2FC") %>%
mutate(sample = gsub( "log2FC_", "", sample)) %>%
separate(sample, into = c("treatment", "replicate"), sep = "-",remove = F) %>%
separate(peptide, into = c("HGNC_Symbol", "Annotated_Sequence"), sep = "_", remove = F ) %>%
group_by(sample, treatment, replicate) %>%
summarise("Mean of patient" = mean(log2FC)) %>%
ungroup() %>%
mutate(treatment = as.factor(treatment)) %>%
mutate(treatment = factor(treatment, levels = c("WT", "G34R", "K27M"))) %>%
ggplot(aes( treatment, `Mean of patient`, fill = treatment )) +
geom_boxplot(outlier.size = 0) +
theme_bw() +
theme(axis.text.x = element_text(angle = 90),
axis.title.x = element_blank()) +
scale_fill_manual(values = PGPalette[c(5,1,2)]) +
ggbeeswarm::geom_beeswarm() +
ggpubr::stat_compare_means(method = "t.test",
comparisons = list(c("WT", "G34R"),
c("WT", "K27M"),
c("K27M", "G34R")) ) +
ggtitle("pST median normalised log2 fold change")pY Mean-Variance Relationship
Set 1
pY_Set1 %>%
mutate(peptide = paste0( HGNC_Symbol, "_", `Annotated Sequence` )) %>%
select(peptide, contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = -peptide) %>%
group_by(peptide) %>%
summarise(mean = mean(value), sd = sd (value) ) %>%
ggplot(aes(mean, sd)) +
xlim(0,10e4) +
ylim(0,10e4) +
#geom_histogram(bins= 200) +
geom_point() +
ggtitle("pY sd vs. mean") +
ggpubr::stat_cor()+
geom_smooth(method = "lm")## Warning: Removed 20 rows containing non-finite values (`stat_cor()`).## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 20 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 20 rows containing missing values (`geom_point()`).
pY_Set1 %>%
mutate(peptide = paste0( HGNC_Symbol, "_", `Annotated Sequence` )) %>%
select(peptide, contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = -peptide) %>%
mutate(log2value = log2(value) ) %>%
group_by(peptide) %>%
summarise(meanlog2 = mean(log2value), sdlog2 = sd (log2value) ) %>%
ggplot(aes(meanlog2, sdlog2)) +
#ylim(0,10e4) +
#scale_x_log10() +
#geom_histogram(bins= 200) +
geom_point() +
ggtitle("pY sd vs. mean") +
ggpubr::stat_cor()+
geom_smooth(method = "lm")## `geom_smooth()` using formula = 'y ~ x'
Set 2
pY_Set2 %>%
mutate(peptide = paste0( HGNC_Symbol, "_", `Annotated Sequence` )) %>%
select(peptide, contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = -peptide) %>%
group_by(peptide) %>%
summarise(mean = mean(value), sd = sd (value) ) %>%
ggplot(aes(mean, sd)) +
xlim(0,10e4) +
ylim(0,10e4) +
#geom_histogram(bins= 200) +
geom_point() +
ggtitle("pY sd vs. mean") +
ggpubr::stat_cor()+
geom_smooth(method = "lm")## Warning: Removed 36 rows containing non-finite values (`stat_cor()`).## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 36 rows containing non-finite values (`stat_smooth()`).## Warning: Removed 36 rows containing missing values (`geom_point()`).
pY_Set2 %>%
mutate(peptide = paste0( HGNC_Symbol, "_", `Annotated Sequence` )) %>%
select(peptide, contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = -peptide) %>%
mutate(log2value = log2(value) ) %>%
group_by(peptide) %>%
summarise(meanlog2 = mean(log2value), sdlog2 = sd (log2value) ) %>%
ggplot(aes(meanlog2, sdlog2)) +
#ylim(0,10e4) +
#scale_x_log10() +
#geom_histogram(bins= 200) +
geom_point() +
ggtitle("pY sd vs. mean") +
ggpubr::stat_cor()+
geom_smooth(method = "lm")## `geom_smooth()` using formula = 'y ~ x'
pY Abundances per peptide
Set 1
pY_Set1 %>%
select(contains("Abundance"), -contains("TMT")) %>%
pivot_longer(names_to = "Channel", cols = everything()) %>%
ggplot(aes(value, fill= Channel)) +
#geom_histogram(bins= 200) +
geom_density(alpha=0.5) +
xlim(0,10e4) +
ggtitle("Raw abundances")## Warning: Removed 374 rows containing non-finite values (`stat_density()`).
Session Info
sessionInfo()## R version 4.2.3 (2023-03-15)
## Platform: x86_64-apple-darwin17.0 (64-bit)
## Running under: macOS Big Sur ... 10.16
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.2/Resources/lib/libRlapack.dylib
##
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## attached base packages:
## [1] stats4 stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] lubridate_1.9.2 forcats_1.0.0
## [3] stringr_1.5.0 dplyr_1.1.2
## [5] purrr_1.0.2 readr_2.1.4
## [7] tidyr_1.3.0 tibble_3.2.1
## [9] ggplot2_3.4.2 tidyverse_2.0.0
## [11] mdatools_0.14.0 SummarizedExperiment_1.28.0
## [13] GenomicRanges_1.50.2 GenomeInfoDb_1.34.9
## [15] MatrixGenerics_1.10.0 matrixStats_1.0.0
## [17] DEP_1.20.0 org.Hs.eg.db_3.16.0
## [19] AnnotationDbi_1.60.2 IRanges_2.32.0
## [21] S4Vectors_0.36.2 Biobase_2.58.0
## [23] BiocGenerics_0.44.0 fgsea_1.24.0
##
## loaded via a namespace (and not attached):
## [1] backports_1.4.1 circlize_0.4.15 fastmatch_1.1-3
## [4] plyr_1.8.8 igraph_1.5.1 gmm_1.8
## [7] splines_4.2.3 shinydashboard_0.7.2 BiocParallel_1.32.6
## [10] digest_0.6.33 foreach_1.5.2 htmltools_0.5.6
## [13] fansi_1.0.4 magrittr_2.0.3 memoise_2.0.1
## [16] cluster_2.1.4 doParallel_1.0.17 tzdb_0.4.0
## [19] limma_3.54.2 ComplexHeatmap_2.14.0 Biostrings_2.66.0
## [22] imputeLCMD_2.1 sandwich_3.0-2 timechange_0.2.0
## [25] colorspace_2.1-0 blob_1.2.4 xfun_0.40
## [28] crayon_1.5.2 RCurl_1.98-1.12 jsonlite_1.8.7
## [31] impute_1.72.3 zoo_1.8-12 iterators_1.0.14
## [34] glue_1.6.2 hash_2.2.6.2 gtable_0.3.3
## [37] zlibbioc_1.44.0 XVector_0.38.0 GetoptLong_1.0.5
## [40] DelayedArray_0.24.0 car_3.1-2 shape_1.4.6
## [43] abind_1.4-5 scales_1.2.1 vsn_3.66.0
## [46] mvtnorm_1.2-2 DBI_1.1.3 rstatix_0.7.2
## [49] Rcpp_1.0.11 plotrix_3.8-2 mzR_2.32.0
## [52] xtable_1.8-4 clue_0.3-64 bit_4.0.5
## [55] preprocessCore_1.60.2 sqldf_0.4-11 MsCoreUtils_1.10.0
## [58] DT_0.28 htmlwidgets_1.6.2 httr_1.4.6
## [61] gplots_3.1.3 RColorBrewer_1.1-3 ellipsis_0.3.2
## [64] farver_2.1.1 pkgconfig_2.0.3 XML_3.99-0.14
## [67] sass_0.4.7 utf8_1.2.3 STRINGdb_2.10.1
## [70] labeling_0.4.2 tidyselect_1.2.0 rlang_1.1.1
## [73] later_1.3.1 munsell_0.5.0 tools_4.2.3
## [76] cachem_1.0.8 cli_3.6.1 gsubfn_0.7
## [79] generics_0.1.3 RSQLite_2.3.1 broom_1.0.5
## [82] evaluate_0.21 fastmap_1.1.1 mzID_1.36.0
## [85] yaml_2.3.7 knitr_1.43 bit64_4.0.5
## [88] caTools_1.18.2 KEGGREST_1.38.0 ncdf4_1.21
## [91] nlme_3.1-163 mime_0.12 compiler_4.2.3
## [94] rstudioapi_0.15.0 beeswarm_0.4.0 png_0.1-8
## [97] ggsignif_0.6.4 affyio_1.68.0 stringi_1.7.12
## [100] bslib_0.5.0 highr_0.10 MSnbase_2.24.2
## [103] lattice_0.21-8 ProtGenerics_1.30.0 Matrix_1.6-0
## [106] tmvtnorm_1.5 vctrs_0.6.3 pillar_1.9.0
## [109] norm_1.0-11.1 lifecycle_1.0.3 BiocManager_1.30.22
## [112] jquerylib_0.1.4 MALDIquant_1.22.1 GlobalOptions_0.1.2
## [115] data.table_1.14.8 cowplot_1.1.1 bitops_1.0-7
## [118] httpuv_1.6.11 R6_2.5.1 pcaMethods_1.90.0
## [121] affy_1.76.0 promises_1.2.1 KernSmooth_2.23-22
## [124] vipor_0.4.5 codetools_0.2-19 MASS_7.3-60
## [127] gtools_3.9.4 assertthat_0.2.1 chron_2.3-61
## [130] proto_1.0.0 rjson_0.2.21 withr_2.5.0
## [133] GenomeInfoDbData_1.2.9 mgcv_1.9-0 parallel_4.2.3
## [136] hms_1.1.3 grid_4.2.3 rmarkdown_2.23
## [139] carData_3.0-5 ggpubr_0.6.0 shiny_1.7.4.1
## [142] ggbeeswarm_0.7.2knitr::knit_exit()